Hugging Face's logo

Brvcket
/
stable-outpainting-xl-decor-0.1

Text-to-Image
Diffusers
TensorBoard
Safetensors
stable-diffusion-xl
stable-diffusion-xl-diffusers
controlnet
diffusers-training
Model card Files Metrics Community
Brvcket commited on
Commit
16a6193
•
1 Parent(s): 6b9778d

End of training

Browse files
Files changed (15) hide show
  1. README.md +39 -0
  2. checkpoint-15000/controlnet/config.json +58 -0
  3. checkpoint-15000/controlnet/diffusion_pytorch_model.safetensors +3 -0
  4. checkpoint-15000/optimizer.bin +3 -0
  5. checkpoint-15000/random_states_0.pkl +3 -0
  6. checkpoint-15000/scaler.pt +3 -0
  7. checkpoint-15000/scheduler.bin +3 -0
  8. config.json +58 -0
  9. diffusion_pytorch_model.safetensors +3 -0
  10. logs/sd_xl_train_controlnet/1730907716.3336074/events.out.tfevents.1730907716.scene-gen-ai-v4-0.17838.1 +3 -0
  11. logs/sd_xl_train_controlnet/1730907716.335028/hparams.yml +54 -0
  12. logs/sd_xl_train_controlnet/1730986452.3393116/events.out.tfevents.1730986452.scene-gen-ai-v4-0.20437.1 +3 -0
  13. logs/sd_xl_train_controlnet/1730986452.3409395/hparams.yml +54 -0
  14. logs/sd_xl_train_controlnet/events.out.tfevents.1730907716.scene-gen-ai-v4-0.17838.0 +3 -0
  15. logs/sd_xl_train_controlnet/events.out.tfevents.1730986452.scene-gen-ai-v4-0.20437.0 +3 -0
README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Brvcket/stable-outpainting-xl-0.1
3
+ library_name: diffusers
4
+ license: openrail++
5
+ tags:
6
+ - stable-diffusion-xl
7
+ - stable-diffusion-xl-diffusers
8
+ - text-to-image
9
+ - diffusers
10
+ - controlnet
11
+ - diffusers-training
12
+ inference: true
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+
19
+ # controlnet-Brvcket/stable-outpainting-xl-decor-0.1
20
+
21
+ These are controlnet weights trained on Brvcket/stable-outpainting-xl-0.1 with new type of conditioning.
22
+
23
+
24
+
25
+ ## Intended uses & limitations
26
+
27
+ #### How to use
28
+
29
+ ```python
30
+ # TODO: add an example code snippet for running this diffusion pipeline
31
+ ```
32
+
33
+ #### Limitations and bias
34
+
35
+ [TODO: provide examples of latent issues and potential remediations]
36
+
37
+ ## Training details
38
+
39
+ [TODO: describe the data used to train the model]
checkpoint-15000/controlnet/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.31.0.dev0",
4
+ "_name_or_path": "alimama-creative/EcomXL_controlnet_inpaint",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "block_out_channels": [
15
+ 320,
16
+ 640,
17
+ 1280
18
+ ],
19
+ "class_embed_type": null,
20
+ "conditioning_channels": 3,
21
+ "conditioning_embedding_out_channels": [
22
+ 16,
23
+ 32,
24
+ 96,
25
+ 256
26
+ ],
27
+ "controlnet_conditioning_channel_order": "rgb",
28
+ "cross_attention_dim": 2048,
29
+ "down_block_types": [
30
+ "DownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "global_pool_conditions": false,
40
+ "in_channels": 4,
41
+ "layers_per_block": 2,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "projection_class_embeddings_input_dim": 2816,
50
+ "resnet_time_scale_shift": "default",
51
+ "transformer_layers_per_block": [
52
+ 1,
53
+ 2,
54
+ 10
55
+ ],
56
+ "upcast_attention": null,
57
+ "use_linear_projection": true
58
+ }
checkpoint-15000/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:283300137c038909f5a867163f94a62085a5d62adffff76ddf65868cd5346133
3
+ size 5004167864
checkpoint-15000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11079578ed1d0bf26d860123f3daf3d3f402f4bcbcca0862ebb26f1a69d5c7f7
3
+ size 10008840997
checkpoint-15000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38647a8446693a1b98cf52413a9c0c5d401f9b2a12a584c5bb00c772289d270c
3
+ size 14727
checkpoint-15000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77383003392fef359e4c672c2186245b3190b499b7d74aabe23618e2051376e5
3
+ size 557
checkpoint-15000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:699fbcbc384dbfd06460e710e35e48ed35154e7f36a4ccae931b52f6273b3408
3
+ size 563
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.31.0.dev0",
4
+ "_name_or_path": "alimama-creative/EcomXL_controlnet_inpaint",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "block_out_channels": [
15
+ 320,
16
+ 640,
17
+ 1280
18
+ ],
19
+ "class_embed_type": null,
20
+ "conditioning_channels": 3,
21
+ "conditioning_embedding_out_channels": [
22
+ 16,
23
+ 32,
24
+ 96,
25
+ 256
26
+ ],
27
+ "controlnet_conditioning_channel_order": "rgb",
28
+ "cross_attention_dim": 2048,
29
+ "down_block_types": [
30
+ "DownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "global_pool_conditions": false,
40
+ "in_channels": 4,
41
+ "layers_per_block": 2,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "projection_class_embeddings_input_dim": 2816,
50
+ "resnet_time_scale_shift": "default",
51
+ "transformer_layers_per_block": [
52
+ 1,
53
+ 2,
54
+ 10
55
+ ],
56
+ "upcast_attention": null,
57
+ "use_linear_projection": true
58
+ }
diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:283300137c038909f5a867163f94a62085a5d62adffff76ddf65868cd5346133
3
+ size 5004167864
logs/sd_xl_train_controlnet/1730907716.3336074/events.out.tfevents.1730907716.scene-gen-ai-v4-0.17838.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60ad7c068c2a57182c0b19a37cdd27ff68c7c0c60d4220fb7c939ea76d51436e
3
+ size 2706
logs/sd_xl_train_controlnet/1730907716.335028/hparams.yml ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ checkpointing_steps: 15000
9
+ checkpoints_total_limit: null
10
+ conditioning_image_column: conditioning_image
11
+ controlnet_model_name_or_path: alimama-creative/EcomXL_controlnet_inpaint
12
+ crops_coords_top_left_h: 0
13
+ crops_coords_top_left_w: 0
14
+ dataloader_num_workers: 0
15
+ dataset_config_name: null
16
+ dataset_name: Brvcket/stable-outpainting-xl-decor-0.1-dataset
17
+ enable_npu_flash_attention: false
18
+ enable_xformers_memory_efficient_attention: false
19
+ gradient_accumulation_steps: 1
20
+ gradient_checkpointing: false
21
+ hub_model_id: null
22
+ hub_token: null
23
+ image_column: image
24
+ learning_rate: 5.0e-06
25
+ logging_dir: logs
26
+ lr_num_cycles: 1
27
+ lr_power: 1.0
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 15000
33
+ mixed_precision: fp16
34
+ num_train_epochs: 2
35
+ num_validation_images: 4
36
+ output_dir: stable-outpainting-xl-decor-0.1
37
+ pretrained_model_name_or_path: Brvcket/stable-outpainting-xl-0.1
38
+ pretrained_vae_model_name_or_path: null
39
+ proportion_empty_prompts: 0
40
+ push_to_hub: true
41
+ report_to: tensorboard
42
+ resolution: 1024
43
+ resume_from_checkpoint: null
44
+ revision: null
45
+ scale_lr: false
46
+ seed: null
47
+ set_grads_to_none: false
48
+ tokenizer_name: null
49
+ tracker_project_name: sd_xl_train_controlnet
50
+ train_batch_size: 1
51
+ train_data_dir: null
52
+ use_8bit_adam: false
53
+ validation_steps: 15000
54
+ variant: null
logs/sd_xl_train_controlnet/1730986452.3393116/events.out.tfevents.1730986452.scene-gen-ai-v4-0.20437.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83bbdf301ba6b37a4e70b29a719eda1ce60b00a6f216fe1f03f9612eb15dfac8
3
+ size 2706
logs/sd_xl_train_controlnet/1730986452.3409395/hparams.yml ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ checkpointing_steps: 15000
9
+ checkpoints_total_limit: null
10
+ conditioning_image_column: conditioning_image
11
+ controlnet_model_name_or_path: alimama-creative/EcomXL_controlnet_inpaint
12
+ crops_coords_top_left_h: 0
13
+ crops_coords_top_left_w: 0
14
+ dataloader_num_workers: 0
15
+ dataset_config_name: null
16
+ dataset_name: Brvcket/stable-outpainting-xl-decor-0.1-dataset
17
+ enable_npu_flash_attention: false
18
+ enable_xformers_memory_efficient_attention: false
19
+ gradient_accumulation_steps: 1
20
+ gradient_checkpointing: false
21
+ hub_model_id: null
22
+ hub_token: null
23
+ image_column: image
24
+ learning_rate: 5.0e-06
25
+ logging_dir: logs
26
+ lr_num_cycles: 1
27
+ lr_power: 1.0
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 15000
33
+ mixed_precision: fp16
34
+ num_train_epochs: 2
35
+ num_validation_images: 4
36
+ output_dir: stable-outpainting-xl-decor-0.1
37
+ pretrained_model_name_or_path: Brvcket/stable-outpainting-xl-0.1
38
+ pretrained_vae_model_name_or_path: null
39
+ proportion_empty_prompts: 0
40
+ push_to_hub: true
41
+ report_to: tensorboard
42
+ resolution: 1024
43
+ resume_from_checkpoint: null
44
+ revision: null
45
+ scale_lr: false
46
+ seed: null
47
+ set_grads_to_none: false
48
+ tokenizer_name: null
49
+ tracker_project_name: sd_xl_train_controlnet
50
+ train_batch_size: 1
51
+ train_data_dir: null
52
+ use_8bit_adam: false
53
+ validation_steps: 15000
54
+ variant: null
logs/sd_xl_train_controlnet/events.out.tfevents.1730907716.scene-gen-ai-v4-0.17838.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a00d80a92f20305338dc6ee1d6b02b9e7acdb9f89247e1cc9bf60acc678c7008
3
+ size 88
logs/sd_xl_train_controlnet/events.out.tfevents.1730986452.scene-gen-ai-v4-0.20437.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:512e73475a51a7905dedcf0a0988d52b6aa54ecf36b9ed57740cc4426c72a3f0
3
+ size 1259834